A machine-learning-based algorithm improves prediction of preeclampsia-associated adverse outcomes

Predicting intensive care need in women with preeclampsia using machine learning - a pilot study

BACKGROUND

Predicting severe preeclampsia with need for intensive care is challenging. To better predict high-risk pregnancies to prevent adverse outcomes such as eclampsia is still an unmet need worldwide. In this study we aimed to develop a prediction model for severe outcomes using routine biomarkers and clinical characteristics.

METHODS

We used machine learning models based on data from an intensive care cohort with severe preeclampsia (n=41) and a cohort of preeclampsia controls (n=40) with the objective to find patterns for severe disease not detectable with traditional logistic regression models.

RESULTS

The best model was generated by including the laboratory parameters aspartate aminotransferase (ASAT), uric acid and body mass index (BMI) with a cross-validation accuracy of 0.88 and an area under the curve (AUC) of 0.91. Our model was internally validated on a test-set where the accuracy was lower, 0.82, with an AUC of 0.85.

CONCLUSION

The clinical routine blood parameters ASAT and uric acid as well as BMI, were the parameters most indicative of severe disease. Aspartate aminotransferase reflects liver involvement, uric acid might be involved in several steps of the pathophysiologic process of preeclampsia, and obesity is a well-known risk factor for development of both severe and non-severe preeclampsia likely involving inflammatory pathways..[Figure: see text].

Trends in antenatal corticosteroid administration: did our timing improve?

OBJECTIVES

We aimed to analyze trends in the rate of effective antenatal corticosteroid prophylaxis (ACS) administrations across a spectrum of typical diagnoses associated with preterm birth.

METHODS

In this retrospective study we utilized delivery data after ACS from 2014 to 2020 at Charité Berlin, Germany. We evaluated the rate of effective ACS administrations defined as ≤10 days between last dose of ACS and delivery as well as the rate of post-ACS births on/after 37 + 0 weeks. We explored conditions associated with high rates of ineffective ACS administrations (>10 days before delivery). We analyzed the trend of ACS-effectiveness during the study period in the overall cohort and in placental dysfunction and cervical insufficiency diagnoses.

RESULTS

The overall rate of effective ACS administrations was 42 % (709/1,672). The overall percentage of deliveries after/at 37 + 0 weeks following ACS administration was 19 % (343). Placenta previa, twin pregnancy and isthmocervical insufficiency were associated with ineffective ACS (19-34 % effective i.e. ≤10 days before delivery). The overall ratio of effective ACS applications rose over time (p=0.002). Over the course of this study ACS effectiveness increased in placental dysfunction and isthmocervical insufficiency diagnoses (p=0.028; p=0.001).

CONCLUSIONS

Compared to a previous publication we found a decrease of post-ACS deliveries after/at 37 + 0 weeks (19 vs. 27 %). Ineffective ACS administrations are still frequent in patients with placenta previa, twin pregnancy and isthmocervical insufficiency. It remains to be investigated in future trials if the introduction of new diagnostic tools such as soluble Fms-like tyrosinkinase-1/placental growth factor (sFlt-1/PlGF) testing and placental alpha-microglobulin-1 (PAMG-1) testing directly led to an increased ACS effectiveness.

Machine learning, advanced data analysis, and a role in pregnancy care? How can we help improve preeclampsia outcomes?

The value of machine learning capacity in maternal health, and in particular prediction of preeclampsia will only be realised when there are high quality clinical data provided, representative populations included, different health systems and models of care compared, and a culture of rapid use and application of real-time data and outcomes. This review has been undertaken to provide an overview of the language, and early results of machine learning in a pregnancy and preeclampsia context. Clinicians of all backgrounds are encouraged to learn the language of Machine Learning (ML) and Artificial intelligence (AI) to better understand their potential and utility to improve outcomes for women and their families. This review will outline some definitions and features of ML that will benefit clinician's knowledge in the preeclampsia discipline, and also outline some of the future possibilities for preeclampsia-focussed clinicians via understanding AI. It will further explore the criticality of defining the risk, and outcome being determined.

An early screening model for preeclampsia: utilizing zero-cost maternal predictors exclusively

To provide a reliable, low-cost screening model for preeclampsia, this study developed an early screening model in a retrospective cohort (25,709 pregnancies) and validated in a validation cohort (1760 pregnancies). A data augmentation method (α-inverse weighted-GMM + RUS) was applied to a retrospective cohort before 10 machine learning models were simultaneously trained on augmented data, and the optimal model was chosen via sensitivity (at a false positive rate of 10%). The AdaBoost model, utilizing 16 predictors, was chosen as the final model, achieving a performance beyond acceptable with Area Under the Receiver Operating Characteristic Curve of 0.8008 and sensitivity of 0.5190. All predictors were derived from clinical characteristics, some of which were previously unreported (such as nausea and vomiting in pregnancy and menstrual cycle irregularity). Compared to previous studies, our model demonstrated superior performance, exhibiting at least a 50% improvement in sensitivity over checklist-based approaches, and a minimum of 28% increase over multivariable models that solely utilized maternal predictors. We validated an effective approach for preeclampsia early screening incorporating zero-cost predictors, which demonstrates superior performance in comparison to similar studies. We believe the application of the approach in combination with high performance approaches could substantially increase screening participation rate among pregnancies. Machine learning model for early preeclampsia screening, using 16 zero-cost predictors derived from clinical characteristics, was built on a 10-year Chinese cohort. The model outperforms similar research by at least 28%; validated on an independent cohort.

Machine learning-enabled maternal risk assessment for women with pre-eclampsia (the PIERS-ML model): a modelling study

BACKGROUND

Affecting 2-4% of pregnancies, pre-eclampsia is a leading cause of maternal death and morbidity worldwide. Using routinely available data, we aimed to develop and validate a novel machine learning-based and clinical setting-responsive time-of-disease model to rule out and rule in adverse maternal outcomes in women presenting with pre-eclampsia.

METHODS

We used health system, demographic, and clinical data from the day of first assessment with pre-eclampsia to predict a Delphi-derived composite outcome of maternal mortality or severe morbidity within 2 days. Machine learning methods, multiple imputation, and ten-fold cross-validation were used to fit models on a development dataset (75% of combined published data of 8843 patients from 11 low-income, middle-income, and high-income countries). Validation was undertaken on the unseen 25%, and an additional external validation was performed in 2901 inpatient women admitted with pre-eclampsia to two hospitals in south-east England. Predictive risk accuracy was determined by area-under-the-receiver-operator characteristic (AUROC), and risk categories were data-driven and defined by negative (-LR) and positive (+LR) likelihood ratios.

FINDINGS

Of 8843 participants, 590 (6·7%) developed the composite adverse maternal outcome within 2 days, 813 (9·2%) within 7 days, and 1083 (12·2%) at any time. An 18-variable random forest-based prediction model, PIERS-ML, was accurate (AUROC 0·80 [95% CI 0·76-0·84] vs the currently used logistic regression model, fullPIERS: AUROC 0·68 [0·63-0·74]) and categorised women into very low risk (-LR <0·1; eight [0·7%] of 1103 women), low risk (-LR 0·1 to 0·2; 321 [29·1%] women), moderate risk (-LR >0·2 and +LR <5·0; 676 [61·3%] women), high risk (+LR 5·0 to 10·0, 87 [7·9%] women), and very high risk (+LR >10·0; 11 [1·0%] women). Adverse maternal event rates were 0% for very low risk, 2% for low risk, 5% for moderate risk, 26% for high risk, and 91% for very high risk within 48 h. The 2901 women in the external validation dataset were accurately classified as being at very low risk (0% with outcomes), low risk (1%), moderate risk (4%), high risk (33%), or very high risk (67%).

INTERPRETATION

The PIERS-ML model improves identification of women with pre-eclampsia who are at lowest and greatest risk of severe adverse maternal outcomes within 2 days of assessment, and can support provision of accurate guidance to women, their families, and their maternity care providers.

FUNDING

University of Strathclyde Diversity in Data Linkage Centre for Doctoral Training, the Fetal Medicine Foundation, The Canadian Institutes of Health Research, and the Bill & Melinda Gates Foundation.

Artificial Intelligence in Early Diagnosis of Preeclampsia

BACKGROUND

Every day, 810 women die of preventable causes related to pregnancy and childbirth worldwide, and preeclampsia is among the top three causes of maternal deaths.

AIM

To develop a diagnostic system with artificial intelligence for the early diagnosis of preeclampsia.

METHODS

This retrospective study included pregnant women who were screened for the inclusion criteria on the hospital's database, and the sample consisted of the data of 1158 pregnant women diagnosed with preeclampsia and 9194 pregnant women who were not diagnosed with preeclampsia at Kahramanmaras Necip Fazıl City Hospital Gynecology and Pediatrics Additional Service Building, Kahramanmaras/Turkey. The statistical analysis was performed using the Statistical Package for social sciences (SPSS) version 22 for windows. Artificial intelligence models were created using Python, scikit-learn, and TensorFlow.

RESULTS

The model achieved 73.7% sensitivity (95% confidence interval (CI): 70.2%-77.1%) and 92.7% specificity (95% CI: 91.7%-93.6%) on the test set. Furthermore, the model had 90.6% accuracy (95% CI: 90.1% - 91.1%) and an area under the curve (AUC) value of 0.832 (95% CI: 0.818-0.846). The significant parameters in predicting preeclampsia in the model were hemoglobin (HGB), age, aspartate transaminase level (AST), alanine transferase level (ALT), and the blood group.

CONCLUSION

Artificial intelligence is effective in the prediction and diagnosis of preeclampsia.

Preeclampsia Prediction Using Machine Learning and Polygenic Risk Scores From Clinical and Genetic Risk Factors in Early and Late Pregnancies

BACKGROUND

Preeclampsia, a pregnancy-specific condition associated with new-onset hypertension after 20-weeks gestation, is a leading cause of maternal and neonatal morbidity and mortality. Predictive tools to understand which individuals are most at risk are needed.

METHODS

We identified a cohort of N=1125 pregnant individuals who delivered between May 2015 and May 2022 at Mass General Brigham Hospitals with available electronic health record data and linked genetic data. Using clinical electronic health record data and systolic blood pressure polygenic risk scores derived from a large genome-wide association study, we developed machine learning (XGBoost) and logistic regression models to predict preeclampsia risk.

RESULTS

Pregnant individuals with a systolic blood pressure polygenic risk score in the top quartile had higher blood pressures throughout pregnancy compared with patients within the lowest quartile systolic blood pressure polygenic risk score. In the first trimester, the most predictive model was XGBoost, with an area under the curve of 0.74. In late pregnancy, with data obtained up to the delivery admission, the best-performing model was XGBoost using clinical variables, which achieved an area under the curve of 0.91. Adding the systolic blood pressure polygenic risk score to the models did not improve the performance significantly based on De Long test comparing the area under the curve of models with and without the polygenic score.

CONCLUSIONS

Integrating clinical factors into predictive models can inform personalized preeclampsia risk and achieve higher predictive power than the current practice. In the future, personalized tools can be implemented to identify high-risk patients for preventative therapies and timely intervention to improve adverse maternal and neonatal outcomes.

New advances in prediction and surveillance of preeclampsia: role of machine learning approaches and remote monitoring

Preeclampsia, a multisystem disorder in pregnancy, is still one of the main causes of maternal morbidity and mortality. Due to a lack of a causative therapy, an accurate prediction of women at risk for the disease and its associated adverse outcomes is of utmost importance to tailor care. In the past two decades, there have been successful improvements in screening as well as in the prediction of the disease in high-risk women. This is due to, among other things, the introduction of biomarkers such as the sFlt-1/PlGF ratio. Recently, the traditional definition of preeclampsia has been expanded based on new insights into the pathophysiology and conclusive evidence on the ability of angiogenic biomarkers to improve detection of preeclampsia-associated maternal and fetal adverse events.However, with the widespread availability of digital solutions, such as decision support algorithms and remote monitoring devices, a chance for a further improvement of care arises. Two lines of research and application are promising: First, on the patient side, home monitoring has the potential to transform the traditional care pathway. The importance of the ability to input and access data remotely is a key learning from the COVID-19 pandemic. Second, on the physician side, machine-learning-based decision support algorithms have been shown to improve precision in clinical decision-making. The integration of signals from patient-side remote monitoring devices into predictive algorithms that power physician-side decision support tools offers a chance to further improve care.The purpose of this review is to summarize the recent advances in prediction, diagnosis and monitoring of preeclampsia and its associated adverse outcomes. We will review the potential impact of the ability to access to clinical data via remote monitoring. In the combination of advanced, machine learning-based risk calculation and remote monitoring lies an unused potential that allows for a truly patient-centered care.

Interpretable machine learning to predict adverse perinatal outcomes: examining marginal predictive value of risk factors during pregnancy

BACKGROUND

The timely identification of nulliparas at high risk of adverse fetal and neonatal outcomes during pregnancy is crucial for initiating clinical interventions to prevent perinatal complications. Although machine learning methods have been applied to predict preterm birth and other pregnancy complications, many models do not provide explanations of their predictions, limiting the clinical use of the model.

OBJECTIVE

This study aimed to develop interpretable prediction models for a composite adverse perinatal outcome (stillbirth, neonatal death, estimated Combined Apgar score of <10, or preterm birth) at different points in time during the pregnancy and to evaluate the marginal predictive value of individual predictors in the context of a machine learning model.

STUDY DESIGN

This was a secondary analysis of the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-be data, a prospective cohort study in which 10,038 nulliparous pregnant individuals with singleton pregnancies were enrolled. Here, interpretable prediction models were developed using L1-regularized logistic regression for adverse perinatal outcomes using data available at 3 study visits during the pregnancy (visit 1: 6 0/7 to 13 6/7 weeks of gestation; visit 2: 16 0/7 to 21 6/7 weeks of gestation; visit 3: 22 0/7 to 29 6/7 weeks of gestation). We identified the important predictors for each model using SHapley Additive exPlanations, a model-agnostic method of computing explanations of model predictions, and evaluated the marginal predictive value of each predictor using the DeLong test.

RESULTS

Our interpretable machine learning model had an area under the receiver operating characteristic curves of 0.617 (95% confidence interval, 0.595-0.639; all predictor variables at visit 1), 0.652 (95% confidence interval, 0.631-0.673; all predictor variables at visit 2), and 0.673 (95% confidence interval, 0.651-0.694; all predictor variables at visit 3). For all visits, the placental biomarker inhibin A was a valuable predictor, as including inhibin A resulted in better performance in predicting adverse perinatal outcomes (P<.001, all visits). At visit 1, endoglin was also a valuable predictor (P<.001). At visit 2, free beta human chorionic gonadotropin (P=.001) and uterine artery pulsatility index (P=.023) were also valuable predictors. At visit 3, cervical length was also a valuable predictor (P<.001).

CONCLUSION

Despite various advances in predictive modeling in obstetrics, the accurate prediction of adverse perinatal outcomes remains difficult. Interpretable machine learning can help clinicians understand how predictions are made, but barriers exist to the widespread clinical adoption of machine learning models for adverse perinatal outcomes. A better understanding of the evolution of risk factors for adverse perinatal outcomes throughout pregnancy is necessary for the development of effective interventions.

The role of artificial intelligence in hypertensive disorders of pregnancy: towards personalized healthcare

INTRODUCTION

Guidelines advise ongoing follow-up of patients after hypertensive disorders of pregnancy (HDP) to assess cardiovascular risk and manage future patient-specific pregnancy conditions. However, there are limited tools available to monitor patients, with those available tending to be simple risk assessments that lack personalization. A promising approach could be the emerging artificial intelligence (AI)-based techniques, developed from big patient datasets to provide personalized recommendations for preventive advice.

AREAS COVERED

In this narrative review, we discuss the impact of integrating AI and big data analysis for personalized cardiovascular care, focusing on the management of HDP.

EXPERT OPINION

The pathophysiological response of women to pregnancy varies, and deeper insight into each response can be gained through a deeper analysis of the medical history of pregnant women based on clinical records and imaging data. Further research is required to be able to implement AI for clinical cases using multi-modality and multi-organ assessment, and this could expand both knowledge on pregnancy-related disorders and personalized treatment planning.

Preeclampsia pathophysiology and adverse outcomes during pregnancy and postpartum

Background

Preeclampsia is a disease with far-reaching consequences that extend beyond the immediate postpartum period and have a significant impact later in life. Preeclampsia exerts an effect on most organ systems in the body. These sequelae are mediated in part by the incompletely elucidated pathophysiology of preeclampsia and the associated vascular changes.

Content

Current research focuses on unraveling the pathophysiology of preeclampsia with the goal of implementing accurate screening and treatment modalities based on disease development and progression. Preeclampsia causes significant short- and long-term maternal morbidity and mortality, not only in the cardiovascular system but also in other organ systems throughout the body. This impact persists beyond pregnancy and the immediate postpartum period.

Summary

The goal of this review is to discuss the current understanding of the pathophysiology of preeclampsia as it relates to the adverse health consequences in patients impacted by this disease, along with a brief discussion of ways to improve overall outcomes.

Prediction of HELLP Syndrome Severity Using Machine Learning Algorithms-Results from a Retrospective Study

(1) Background: HELLP (hemolysis, elevated liver enzymes, and low platelets) syndrome is a rare and life-threatening complication of preeclampsia. The aim of this study was to evaluate and compare the predictive performances of four machine learning-based models for the prediction of HELLP syndrome, and its subtypes according to the Mississippi classification; (2) Methods: This retrospective case-control study evaluated pregnancies that occurred in women who attended a tertiary maternity hospital in Romania between January 2007 and December 2021. The patients' clinical and paraclinical characteristics were included in four machine learning-based models: decision tree (DT), naïve Bayes (NB), k-nearest neighbors (KNN), and random forest (RF), and their predictive performance were assessed; (3) Results: Our results showed that HELLP syndrome was best predicted by RF (accuracy: 89.4%) and NB (accuracy: 86.9%) models, while DT (accuracy: 91%) and KNN (accuracy: 87.1%) models had the highest performance when used to predict class 1 HELLP syndrome. The predictive performance of these models was modest for class 2 and 3 of HELLP syndrome, with accuracies ranging from 65.2% and 83.8%; (4) Conclusions: The machine learning-based models could be useful tools for predicting HELLP syndrome, and its most severe form-class 1.

Predictive Performance of Machine Learning-Based Methods for the Prediction of Preeclampsia-A Prospective Study

(1) Background: Preeclampsia (PE) prediction in the first trimester of pregnancy is a challenge for clinicians. The aim of this study was to evaluate and compare the predictive performances of machine learning-based models for the prediction of preeclampsia and its subtypes. (2) Methods: This prospective case-control study evaluated pregnancies that occurred in women who attended a tertiary maternity hospital in Romania between November 2019 and September 2022. The patients' clinical and paraclinical characteristics were evaluated in the first trimester and were included in four machine learning-based models: decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF), and their predictive performance was assessed. (3) Results: Early-onset PE was best predicted by DT (accuracy: 94.1%) and SVM (accuracy: 91.2%) models, while NB (accuracy: 98.6%) and RF (accuracy: 92.8%) models had the highest performance when used to predict all types of PE. The predictive performance of these models was modest for moderate and severe types of PE, with accuracies ranging from 70.6% and 82.4%. (4) Conclusions: The machine learning-based models could be useful tools for EO-PE prediction and could differentiate patients who will develop PE as early as the first trimester of pregnancy.

Development of a prediction model on preeclampsia using machine learning-based method: a retrospective cohort study in China

Objective: The aim of this study was to use machine learning methods to analyze all available clinical and laboratory data obtained during prenatal screening in early pregnancy to develop predictive models in preeclampsia (PE).

Material and Methods: Data were collected by retrospective medical records review. This study used 5 machine learning algorithms to predict the PE: deep neural network (DNN), logistic regression (LR), support vector machine (SVM), decision tree (DT), and random forest (RF). Our model incorporated 18 variables including maternal characteristics, medical history, prenatal laboratory results, and ultrasound results. The area under the receiver operating curve (AUROC), calibration and discrimination were evaluated by cross-validation.

Results: Compared with other prediction algorithms, the RF model showed the highest accuracy rate. The AUROC of RF model was 0.86 (95% CI 0.80–0.92), the accuracy was 0.74 (95% CI 0.74–0.75), the precision was 0.82 (95% CI 0.79–0.84), the recall rate was 0.42 (95% CI 0.41–0.44), and Brier score was 0.17 (95% CI 0.17–0.17).

Conclusion: The machine learning method in our study automatically identified a set of important predictive features, and produced high predictive performance on the risk of PE from the early pregnancy information.